Explore live open-source projects and AI models.

ROCm/AMD GPU benchmark suite for llama.cpp, whisper.cpp, PyTorch

A beautifully crafted desktop client for running and managing local LLMs via llama.cpp.

一个简单的基于llama.cpp的c#仿chatgpt的本地部署demo

Ollama-shape inference manager using Tom's TurboQuant llama.cpp. FIFO queue + grace + IDLE_HOT hot-hold + model swap on Blackwell.

An Android app using whisper.cpp for voice-to-text transcription

A wrapping of paho cpp (https://www.eclipse.org/paho/) able to make MQTT clients in Godot.

A FastApi-style framework for Cpp

A script for bundling small C++ projects into a single file, to upload to CodinGame, by resolving includes, include guards, and accompanying .cpp files

🎤 Privacy-first local speech-to-text dictation for NixOS - Whisper.cpp powered push-to-talk with real-time feedback

World's first TurboQuant KV cache compression for llama.cpp on AMD ROCm (RX 9070 / gfx1201)